© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70439
    Prev
    Next
    INDEX
    Explanations

    three-phase motor

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on mentions of electrical “phase” systems—especially when paired with numeric or descriptive qualifiers like “three-phase,” “single-phase,” or “multi-phase.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     want
    -1.62
     until
    -1.47
     won
    -1.46
     already
    -1.45
     could
    -1.42
     Isn
    -1.35
     before
    -1.33
     puntata
    -1.33
     也
    -1.30
    ziest
    -1.30
    POSITIVE LOGITS
    at
    1.31
     trajo
    1.28
     ","
    1.27
    ,»
    1.25
     _,
    1.25
    '
    1.24
    ,‎
    1.23
     -,
    1.22
    \
    1.22
     \&
    1.21
    Activations Density 0.023%

    No Known Activations